Machine Learning and Deep Learning with R

Poo Kuan Hoong

February 15, 2017

Deep Learning so far…

In the past 10 years, machine learning and Artificial Intelligence (AI) have shown tremendous progress
The recent success can be attributed to:
- Explosion of data
- Cheap computing cost - CPUs and GPUs
- Improvement of machine learning models
Much of the current excitement concerns a subfield of it called “deep learning”.

Deep Learning is primarily about neural networks, where a network is an interconnected web of nodes and edges.
Neural nets were designed to perform complex tasks, such as the task of placing objects into categories based on a few attributes.
Neural nets are highly structured networks, and have three kinds of layers - an input, an output, and so called hidden layers, which refer to any layers between the input and the output layers.
Each node (also called a neuron) in the hidden and output layers has a classifier.

Deep learning refers to artificial neural networks that are composed of many layers.
It’s a growing trend in Machine Learning due to some favorable results in applications where the target function is very complex and the datasets are large.

Robust
- No need to design the features ahead of time - features are automatically learned to be optimal for the task at hand
- Robustness to natural variations in the data is automatically learned
Generalizable
- The same neural net approach can be used for many different applications and data types
Scalable
- Performance improves with more data, method is massively parallelizable

Deep Learning requires a large dataset, hence long training period.
In term of cost, Machine Learning methods like SVMs and other tree ensembles are very easily deployed even by relative machine learning novices and can usually get you reasonably good results.
Deep learning methods tend to learn everything. It’s better to encode prior knowledge about structure of images (or audio or text).
The learned features are often difficult to understand. Many vision features are also not really human-understandable (e.g, concatenations/combinations of different features).
Requires a good understanding of how to model multiple modalities with traditional tools.

MXNet: The R interface to the MXNet deep learning library.
darch: An R package for deep architectures and restricted Boltzmann machines.
deepnet: An R package implementing feed-forward neural networks, restricted Boltzmann machines, deep belief networks, and stacked autoencoders.
h2o: The R interface to the H2O deep-learning framework.

MXNet supports the R programming language.
Flexible and efficient GPU computing and state-of-art deep learning to R.
Seamless tensor/matrix computation with multiple GPUs in R.
Construct and customize the state-of-art deep learning models in R, and apply them to tasks, such as image classification and data science challenges
MXNet Package can be downloaded using the following commands:

install.packages("drat", repos="https://cran.rstudio.com")
drat:::addRepo("dmlc")
install.packages("mxnet")

The MNIST database consists of handwritten digits.
The training set has 60,000 examples, and the test set has 10,000 examples.
The MNIST database is a subset of a larger set available from NIST. The digits have been size-normalized and centered in a fixed-size image
For this demo, the Kaggle pre-processed training and testing dataset were used. The training dataset, (train.csv), has 42000 rows and 785 columns.